搅拌摩擦焊前导点温度控制研究  

Research on Temperature Control of Leading Point in Friction Stir Welding

作　　者：张喆 张永林[1] 周扬 陈书锦[2] ZHANG Zhe;ZHANG Yonglin;ZHOU Yang;CHEN Shujin(School of Electronic Information,Jiangsu University of Science and Technology,Zhenjiang 212000,China;School of Materials Science and Engineering,Jiangsu University of Science and Technology,Zhenjiang 212000,China)

机构地区：[1]江苏科技大学电子信息学院,江苏镇江212000 [2]江苏科技大学材料科学与工程学院,江苏镇江212000

出　　处：《热加工工艺》2021年第3期110-114,共5页Hot Working Technology

基　　金：国家自然科学基金资助项目(51675248);江苏省研究生科研与实践创新计划项目(SJCX180774)。

摘　　要：现有搅拌摩擦焊多为开环控制系统,对焊接温度的控制不能满足工艺要求。选用5083铝合金进行焊接温度实验,利用遗传BP神经网络算法建立搅拌摩擦焊前导点温度模型。在模型基础上,在外部闭环中使用模糊控制器调节搅拌头转速,在内部闭环中使用预测控制器解决温度延迟问题,构建双闭环的搅拌摩擦焊温度控制系统。结果表明,搅拌摩擦焊温度控制系统可有效追踪目标温度,将焊接温度控制在理想区间,且具有高效率的转速调节,不易造成机械损伤。The existing friction stir welding is mostly an open loop control system, and the control of the welding temperature cannot meet the process requirements. 5083 aluminum alloy was used in the welding temperature experiment, and the genetic BP neural network algorithm was used to establish the temperature model of the friction stir welding front guide point. On the basis of the model, the fuzzy controller was used to adjust the stirring head speed in the external closed loop and the predictive controller was used to solve the temperature delay problem in the internal closed loop to construct a double closed loop friction stir welding temperature control system. The results show that the friction stir welding temperature control system can effectively track the target temperature, control the welding temperature in the ideal interval, and have high efficiency adjustment of the speed, which is not easy to cause mechanical damage.

关 键 词：搅拌摩擦焊 遗传BP神经网络 模糊控制 模型预测控制 

分 类 号：TG453.9[金属学及工艺—焊接]